Skip to content
English

Switch theme

// Meituan LongCat · Text-to-speech / audio

LongCat-AudioDiT-1B: VRAM & local deployment

1.42B parameters. About 1.4 GB at 4-bit and 3.6 GB at BF16.

released 2026-03-30licence: Commercial OKmemory figures are estimates

01Specs

PublisherMeituan · meituan-longcat
Family / seriesMeituan LongCat · LongCat-AudioDiT
TypeText-to-speech / audio
Parameters1.42B Source: counted from official safetensors weights
Released weightsFP32 · 5.7 GBdownload
LicenceMIT · Commercial OKPermissive licence (Apache-2.0 / MIT / CC-BY / OpenMDW): commercial use allowed.
Released2026-03-30 (Hugging Face repo created)

02How much VRAM it needs (estimate)

Audio models are small; the weight size is close to the total memory needed.

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)2.8 GB 3.6 GB 8GB GPUMac 16GB
FP8 / INT8 / Q8_01.5 GB 2.2 GB 8GB GPUMac 16GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)0.9 GB 1.4 GB 8GB GPUMac 16GB

Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →

03How to run it

Only runtimes the publisher or the runtime’s official library names for this model.

Which inference engine to choose →

04Official repositories & quantised builds

1 official repo(s) from meituan-longcat.

05Other Meituan LongCat models

All 16 →
ModelParams4-bit totalReleased
LongCat-AudioDiT-3.5B · same series3.83B3.1 GB2026-03-30
LongCat-Flash-Lite-Sparse69B / 3B46.6 GB2026-07-31
LongCat-2.01.6T / 48B1.07 TB2026-07-05
LongCat-Image-Edit-Turbo——2026-02-03
LongCat-Flash-Lite68.5B / 3B46.3 GB2026-01-27
LongCat-Flash-Thinking-ZigZag561.9B376 GB2026-01-23
LongCat-Flash-Thinking-2601560B / 27B374 GB2026-01-14
LongCat-HeavyMode-Summary561.9B376 GB2026-01-14
LongCat-Image-Edit——2025-12-05

06Sources

Data checked 2026-04-03. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

Data updated: Self-host open models(UTC+8)